Reinforcement Learning from Scratch

Welcome to my Reinforcement Learning (RL) Playground! This repository is a personal project where I implement various RL algorithms from scratch, purely for fun and learning. The goal is to build a solid intuition behind RL concepts by implementing them step by step, without relying on high-level libraries.

📌 Implemented Algorithms

Dynamic Programming & Classical Methods

• ✅ Value Iteration
• ✅ Policy Iteration
• ✅ Monte Carlo Methods
• ✅ Temporal Difference (TD) Learning

Tabular RL

• ✅ Q-Learning
• ✅ SARSA

Deep Reinforcement Learning (DRL)

• ✅ Deep Q-Network (DQN)
• ✅ REINFORCE (Monte Carlo Policy Gradient)

Advanced RL (SOTA)

• 🔄 Proximal Policy Optimization (PPO) (planned)
• 🔄 Deep Determinstic Policy Gradient (DDPG) (planned)
• 🔄 Twin-Delayed Deep Determinstic Policy Gradient (TD3) (planned)
• 🔄 Soft Actor-Critic (SAC) (planned)